Menu

Welcome!

I am Juan Antonio Bellido Jiménez

Engineer, lecturer and researcher at University of Córdoba

About

Juan Antonio Bellido Jiménez

Hi! I am a PhD student working on outperforming agrometeorological estimates and forecasts using machine learning models at the University of Córdoba under supervision of Javier Estévez Gualda and Amanda Penélope García Marín.

Portrait picture of Juan Antonio Bellido Jiménez

Software

Software projects of which I am the author, or a core contributor.

AgroML: Agronomy Machine Learning

Paper, code, and documentation.

Agronomy Machine Learning An easy tool for developing estimations and forecasts of agro-meteorological variables (solar radiation, reference evapotranspiration, precipitation, aridity index) using different machine learning models.

Publications

My most recent publications, titles link an overview page. For citations, see Google Scholar.

Agronomy 2022

AgroML: An Open-Source Repository to Forecast Reference Evapotranspiration in Different Geo-Climatic Conditions Using Machine Learning and Transformer-Based Models

Juan Antonio Bellido-Jiménez, Javier Estévez, Joaquin Vanschoren and Amanda Penélope García-Marín

Accurately forecasting reference evapotranspiration (ET0) values is crucial to improve crop irrigation scheduling, allowing anticipated planning decisions and optimized water resource management and agricultural production. In this work, a recent state-of-the-art architecture has been adapted and deployed for multivariate input time series forecasting (transformers) using past values of ET0 and temperature-based parameters (28 input configurations) to forecast daily ET0 up to a week (1 to 7 days)....

Atmosphere 2021

Assessing Machine Learning Models for Gap Filling Daily Rainfall Series in a Semiarid Region of Spain

Juan Antonio Bellido-Jiménez, Javier Estévez, Amanda Penélope García-Marín

The presence of missing data in hydrometeorological datasets is a common problem, usually due to sensor malfunction, deficiencies in records storage and transmission, or other recovery procedures issues. These missing values are the primary source of problems when analyzing and modeling their spatial and temporal variability. Thus, accurate gap-filling techniques for rainfall time series are necessary to have complete datasets, which is crucial in studying climate change evolution...

Water 2020

Monthly Precipitation Forecasts Using Wavelet Neural Networks Models in a Semiarid Environment

Juan Antonio Bellido-Jiménez, Javier Estévez, Amanda Penélope García-Marín

Accurate forecast of hydrological data such as precipitation is critical in order to provide useful information for water resources management, playing a key role in different sectors. Traditional forecasting methods present many limitations due to the high-stochastic property of precipitation and its strong variability in time and space: not identifying non-linear dynamics or not solving the instability of local weather situations...

Congreso Internacional Multidisciplicar de Investigadores en Formación 2020

New machine learning methods applied to enhance reference evapotranspiration estimates in a humid environment

Juan Antonio Bellido-Jiménez, Javier Estévez, Amanda Penélope García-Marín

Estimating reference evapotranspiration (ET0) is crucial for water resources management and irrigation scheduling, being of special importance in areas with water resource scarcity and developing countries/regions. The use of models based on Artificial Intelligence has been widely applied, especially in estimations and forecasts of agrometeorological parameters like solar radiation, precipitation...

Dortmund International Research Conference 2020

Assessing bayesian optimization and grid-search tuning of hyperparameters in a neural network model to estimate reference evapotranspiration with a low-cost sensor

Juan Antonio Bellido-Jiménez, Javier Estévez, Amanda Penélope García-Marín

The present work analyses the performance of low-cost temperature and relative humidity sensor to estimate ET0 with MLP in one location situated in Southern Spain (where a conventional agrometeorological station works properly), while assessing the differences in accuracy and computational cost due to tune hyperparameters with Grid-Search and Bayesian optimization

Agricultural Water Management 2021

New machine learning approaches to improve reference evapotranspiration estimates using intra-daily temperature-based variables in a semi-arid region of Spain

Juan Antonio Bellido-Jiménez, Javier Estévez, Amanda Penélope García-Marín

The estimation of Reference Evapotranspiration (ET0) is crucial to estimate crop water requirements, especially in developing countries and areas with scarce water resources. In these regions, the impossibility of collecting all the required data to compute FAO-56 Penman–Monteith equation (FAO56-PM) makes scientists search new methodologies to accurately estimate ET0 with the minimum number of climatic parameters....

Applied Energy 2021

Assessing new intra-daily temperature-based machine learning models to outperform solar radiation predictions in different conditions

Juan Antonio Bellido-Jiménez, Javier Estévez, Amanda Penélope García-Marín

The measure of solar radiation is costly, as well as its maintenance and calibration needs; therefore, reliable datasets are scarce. In this work, several machine learning models to predict solar radiation have been developed and assessed at nine locations (Southern Spain and North Carolina in the USA), representing different geo-climatic conditions (aridity, sea distance, and elevation)...

The 3rd International Electronic Conference on Atmospheric Sciences 2020

Assessing Neural Network Approaches for Solar Radiation Estimates Using Limited Climatic Data in the Mediterranean Sea

Juan Antonio Bellido-Jiménez, Javier Estévez, Amanda Penélope García-Marín

One of the most crucial variables in agricultural meteorology is solar radiation (Rs), although it is measured in a very limited number of weather stations due to its high cost in both installation and maintenance. Moreover, the quality of the data is usually low because of sensor failure and/or lack of calibration, which made scientists search for new approaches such as neural network models...

International Conference on Time Series and Forecasting 2019

Assessing Wavelet Analysis for Precipitation Forecasts Using Artificial Neural Networks in Mediterranean Coast

Javier Estévez, Juan Antonio Bellido-Jiménez, Xiaodong Liu , Amanda Penélope García-Marín

Precipitation is one of the most important variables needed in different hydrological models: infiltration, soil loss, droughts, overland flow production, floods, etc. To predict its behavior is complex due to it is highly intermittent over time. Because of the adequate time-frequency representation of wavelet techniques, they are being widely applied to different hydrological resources applications....